Cryptocurrency Forecasting: A Comparative Study of Machine Learning and Deep Learning Approaches
Al-Farooq Journal of Sciences · 30.06.2026 · 2 (3) · 1728-1736
DOI: 10.65405/76e4gv75 ↗Kurz gefasst
Fachartikel in der Zeitschrift Al-Farooq Journal of Sciences, online erschienen am 30.06.2026. Verfasst von Hani Amr Alatoushi und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
In today’s financial landscape, understanding and predicting cryptocurrency trends are of utmost importance due to the significant growth of digital currencies. This paper delves into a comprehensive study of predictive modeling for six major cryptocurrencies: Bitcoin, Dogecoin, Ethereum, USDCoin, BinanceCoin, and Cardanocoin. Using a wide range of machine learning and deep learning algorithms, we carefully assess how well each model can capture the complex nature of cryptocurrency markets. We employed a rigorous methodology, including models like Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNN), Support Vector Machines (SVM), and eXtreme Gradient Boosting (XGBoost), among others. We evaluated each model’s performance using standard metrics like RMSE and R². The results show that different models perform differently, with some algorithms excelling in predicting specific cryptocurrencies.
Zitieren
APA
Alatoushi, H. A., & Abokhnana, S. A. (2026). Cryptocurrency Forecasting: A Comparative Study of Machine Learning and Deep Learning Approaches. Al-Farooq Journal of Sciences, 2(3), 1728-1736. https://doi.org/10.65405/76e4gv75
Vancouver
Alatoushi HA, Abokhnana SA. Cryptocurrency Forecasting: A Comparative Study of Machine Learning and Deep Learning Approaches. Al-Farooq Journal of Sciences. 2026;2(3):1728-1736. doi:10.65405/76e4gv75
BibTeX
@article{Alatoushi2026,
author = {Alatoushi, Hani Amr and Abokhnana, Sherhan Aiad},
title = {Cryptocurrency Forecasting: A Comparative Study of Machine Learning and Deep Learning Approaches},
journal = {Al-Farooq Journal of Sciences},
year = {2026},
volume = {2},
number = {3},
pages = {1728--1736},
doi = {10.65405/76e4gv75}
}
EUVIMED